Contextual Transformer Networks for Visual Recognition

单位：JD AI Research

作者：Yehao Li, Ting Yao, Yingwei Pan, and Tao Mei

发表：Arxiv ( Rank 1 in open-set image classification task of Open World Vision Challenge @ CVPR 2021)

摘要

阅读

论文的目的及结论

论文的实验

论文的方法

总结

论文的贡献

论文的不足

论文如何讲故事

参考资料

• https://arxiv.org/abs/2107.12292

• https://github.com/JDAI-CV/CoTNet